Pith. sign in

REVIEW 12 cited by

Deciphering antibody affinity maturation with language models and weakly supervised learning

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2112.07782 v1 pith:MRZVQWVZ submitted 2021-12-14 q-bio.BM cs.LG

classification q-bio.BMcs.LG
keywords antibodiesimmunelanguagemodelssequencesaffinityantibodybinding
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

In response to pathogens, the adaptive immune system generates specific antibodies that bind and neutralize foreign antigens. Understanding the composition of an individual's immune repertoire can provide insights into this process and reveal potential therapeutic antibodies. In this work, we explore the application of antibody-specific language models to aid understanding of immune repertoires. We introduce AntiBERTy, a language model trained on 558M natural antibody sequences. We find that within repertoires, our model clusters antibodies into trajectories resembling affinity maturation. Importantly, we show that models trained to predict highly redundant sequences under a multiple instance learning framework identify key binding residues in the process. With further development, the methods presented here will provide new insights into antigen binding from repertoire sequences alone.

Discussion (0). Sign in to comment.

Forward citations

Cited by 12 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. EpiFormer: Learning Antigen-Antibody Interactions for Epitope Prediction via Geometric Deep Learning

    q-bio.QM 2026-06 unverdicted novelty 7.0 of 10

    EpiFormer improves epitope prediction F1 score by over 40% via early-fusion cross-attention in GNN layers and sparsity-aware objectives, while recovering known biology as emergent behavior.

  2. ConTact: Contact-First Antibody CDR Design via Explicit Interface Reasoning

    cs.LG 2026-05 unverdicted novelty 7.0 of 10

    ConTact decomposes CDR design into surface fingerprint learning, contact prediction, and contact-gated sequence generation using distance-biased attention and weighted loss, reporting 7% RMSD and 10% F1 gains on CHIME...

  3. ConTact: Contact-First Antibody CDR Design via Explicit Interface Reasoning

    cs.LG 2026-05 unverdicted novelty 7.0 of 10

    ConTact introduces a contact-then-act architecture with distance-biased cross-attention and contact-weighted loss for antibody CDR design, reporting 5-6% better backbone RMSD and superior contact metrics on CHIMERA-Be...

  4. Conditional generation of antibody sequences with classifier-guided germline-absorbing discrete diffusion

    cs.LG 2026-05 unverdicted novelty 7.0 of 10

    Germline-absorbing discrete diffusion uses the germline sequence as the absorbing state to reduce germline bias in antibody modeling, raising non-germline residue prediction accuracy from 26% to 46% and improving cond...

  5. Surveying the adaptive landscapes of 10,000 antibodies

    q-bio.PE 2026-06 unverdicted novelty 6.0 of 10

    A parameter-free framework applied to over 10,000 public antibody clonotypes identifies clonotype-dependent positive selection, a prevalence-fitness tradeoff, and reproduces convergent mutation patterns for SARS-CoV-2...

  6. AgForce Enables Antigen-conditioned Generative Antibody Design

    cs.LG 2026-05 unverdicted novelty 6.0 of 10

    AgForce improves antigen-conditioned antibody design by using framework dropout, gated bottlenecks, hyperbolic cross attention, MDN sequence head with Potts-like coupling, annealed MCL, and antigen cycle consistency t...

  7. EvoStruct: Bridging Evolutionary and Structural Priors for Antibody CDR Design via Protein Language Model Adaptation

    cs.LG 2026-05 unverdicted novelty 6.0 of 10

    EvoStruct integrates evolutionary priors from a protein language model with structural priors from an E(3)-equivariant GNN to raise amino acid recovery by 16% and diversity by 2.3x on CHIMERA-Bench while cutting perpl...

  8. Antigen-specific Antibody Multi-modal Foundation Model for Functional Antibody Design

    q-bio.BM 2026-07 reject novelty 5.0 of 10

    AAMFM combines ESM3, an antigen-geometry adapter, and Cal-DPO preference optimization rewarded by AlphaFold3-style scores to design antibody CDRs and structures, reporting higher predicted binding scores than prior methods.

  9. Computational Modeling of Antibody-Antigen Complexes: PLM-Based and MSA-Based Approaches

    q-bio.QM 2026-05 unverdicted novelty 5.0 of 10

    PLM embeddings improve antibody monomer CDR-H3 accuracy but fail on complexes without co-evolution signals, while MSA refinement and convergence-aware recycling yield gains over AlphaFold3 on held-out antibody-antigen...

  10. AbLWR:A Context-Aware Listwise Ranking Framework for Antibody-Antigen Binding Affinity Prediction via Positive-Unlabeled Learning

    cs.LG 2026-04 unverdicted novelty 5.0 of 10

    AbLWR turns affinity prediction into listwise ranking with positive-unlabeled learning and context-aware attention, claiming over 10% better Precision@1 than baselines on cross-validation and case studies for influenz...

  11. Biologically-Grounded Multi-Encoder Architectures as Developability Oracles for Antibody Design

    q-bio.BM 2026-04 unverdicted novelty 5.0 of 10

    CrossAbSense oracles using frozen PLM encoders plus self- or cross-attention decoders improve prediction accuracy by 12-20% on three of five developability assays for therapeutic IgGs, with architecture choices reveal...

  12. Conditionally Site-Independent Neural Evolution of Antibody Sequences

    cs.LG 2026-02 conditional novelty 5.0 of 10

    A neural continuous-time Markov model of antibody affinity maturation that beats language models on fitness prediction and steers sampling toward antigen-specific binders.

Pith tools